Service
Health--
Auth--
Model--
Compute
Device--
CUDA--
Loaded--
CPU
Usage--
Cores--
Memory
Usage--
Disk--
Usage Timeline
CPU
Memory
Disk
LLM request
Waiting for data
Speech To Text
Sherpa VAD
Speaker Verify
Text To Speech
Select an info button to inspect impact and behavior.
TTS Provider Control
| Provider | State | Quality | Languages | License | Risk | Action |
|---|---|---|---|---|---|---|
| Loading providers | ||||||
Import Piper Voice
Active Tasks
| Task | Status | PID | Runtime | CPU | Memory | Details | Action |
|---|---|---|---|---|---|---|---|
| No tasks | |||||||
LLM Gateway
Status--
Runtime--
Default model--
Serving--
Local Runtime
llama.cpp--
Ollama--
Installed--
Version--
Governed LLM Tools
No LLM run yet.
Installed Models
| Model | Family | Parameters | Quantization | Size | Capabilities |
|---|---|---|---|---|---|
| No model data loaded | |||||
LLM Request History
| Time | Provider | Service | Model | Endpoint | Status | Usage | Duration | Error |
|---|
| Time | Action | Service | Status | Duration | Details |
|---|
| Time | Type | Service | Status | Duration | Error |
|---|
TTS Benchmarks
| Time | Provider | Voice | Audio | Generation | RTF | Rating |
|---|
Speech Benchmarks
| Time | Operation | Provider | Model | Audio | Latency | RTF | Peak CPU | Peak Memory |
|---|